INDEX

Explanations

terms related to biological processes and research results

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Tokens before words related to medical or scientific processes

np_acts-logits-general · gemini-2.0-flash

continuous administration or movement

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.92

InitVars

-0.85

 Jefus

-0.82

protoc

-0.78

 kaarangay

-0.77

featureID

-0.77

 createSlice

-0.74

 beginnetje

-0.73

RUnlock

-0.71

évaluateur

-0.71

POSITIVE LOGITS

การ

0.89

 történ

0.67

 sự

0.61

 further

0.60

further

0.59

からの

0.58

 việc

0.57

 való

0.57

での

0.56

への

0.56

Activations Density 2.250%

terms related to biological processes and research results

Tokens before words related to medical or scientific processes

continuous administration or movement

No Comments

No Known Activations